© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12907
    Prev
    Next
    INDEX
    Explanations

    biological terms related to cellular functions and transport mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pres
    -0.39
     everywhere
    -0.37
     PRES
    -0.36
     prescription
    -0.34
     Pres
    -0.33
    ѓ
    -0.33
    enumii
    -0.33
     waiting
    -0.32
     Trend
    -0.32
     ريال
    -0.31
    POSITIVE LOGITS
    DockStyle
    0.79
    AndEndTag
    0.75
    transQ
    0.63
    tagHelperRunner
    0.63
    WithIOException
    0.60
    featureID
    0.58
     ProtoMessage
    0.57
    InjectAttribute
    0.56
    providedIn
    0.56
    Portail
    0.55
    Activations Density 2.499%

    No Known Activations